microsoft-graph-api
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Recommends the global installation of the official
@membranehq/cliutility from the npm registry to facilitate communication with the platform. - [COMMAND_EXECUTION]: The skill instructs the agent to execute specific CLI commands such as
membrane login,membrane connect, andmembrane action runfor managing Microsoft Graph API connections and performing data operations. - [PROMPT_INJECTION]: Identified an indirect prompt injection surface as the skill retrieves and processes data from external Microsoft 365 services (emails, drives, contacts) which may contain user-generated content.
- Ingestion points: Data returned from Microsoft Graph API calls processed in SKILL.md.
- Boundary markers: None specified in the instructions.
- Capability inventory: The skill utilizes
membrane action runandmembrane requestfor executing API actions and proxying network requests. - Sanitization: No explicit validation or filtering of incoming API data is documented.
Audit Metadata